Leveraging affinity cycle consistency to isolate factors of variation in learned representations

Identifying the dominant factors of variation across a dataset is a central goal of representation learning . Key insight is the use of affinity cycle consistency (ACC) between the learned embeddings of images belonging to different sets . We demonstrate the applicability of ACC to the tasks of digit style isolation and synthetic-to-real object pose transfer. In contrast to prior work, we demonstrate that we can work with significantly fewer constraints on the factors of . variation, and in some cases, with almost no constraints on . the factors . of variation for part of the data, we quantify the effectiveness of ACC through mutual information . between the . learned representations and the known image generative factors. In addition to . the learned representations, we . demonstrate the . usefulness of ACC, we demonstrate the effectiveness of ACC is to the . effectiveness ofACC to the functions of digit styles isolation and . to the task of . the . tasks of . digit style isolate and synthetic

Links: PDF - Abstract

Code :

None

Keywords : factors - acc - learned - variation - demonstrate -

Leave a Reply

Your email address will not be published. Required fields are marked *